{"id":"https://openalex.org/W7166816111","doi":"https://doi.org/10.18653/v1/2026.acl-long.703","title":"When Vision-Language Models Judge Without Seeing: Exposing Informativeness Bias","display_name":"When Vision-Language Models Judge Without Seeing: Exposing Informativeness Bias","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166816111","doi":"https://doi.org/10.18653/v1/2026.acl-long.703"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.703","doi":"https://doi.org/10.18653/v1/2026.acl-long.703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.703","pdf_url":"https://aclanthology.org/2026.acl-long.703.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.703.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132571483","display_name":"Xiaohan Zou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohan Zou","raw_affiliation_strings":["The Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134349727","display_name":"Roshan Sridhar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roshan Sridhar","raw_affiliation_strings":["Oracle AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134261039","display_name":"Mohammadtaher Safarzadeh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammadtaher Safarzadeh","raw_affiliation_strings":["Oracle AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139816959","display_name":"Dan Roth","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Roth","raw_affiliation_strings":["Oracle AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oracle AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8958,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97399374,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"15417","last_page":"15448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.609000027179718},{"id":"https://openalex.org/keywords/birch","display_name":"birch","score":0.9100000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4115000069141388},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.28369998931884766},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25060001015663147},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24699999392032623},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.24549999833106995}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.703","doi":"https://doi.org/10.18653/v1/2026.acl-long.703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.703","pdf_url":"https://aclanthology.org/2026.acl-long.703.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.703","doi":"https://doi.org/10.18653/v1/2026.acl-long.703","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.703","pdf_url":"https://aclanthology.org/2026.acl-long.703.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","score":0.4711971580982208,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166816111.pdf","grobid_xml":"https://content.openalex.org/works/W7166816111.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7219155369","https://openalex.org/W4402670365","https://openalex.org/W7214928221","https://openalex.org/W4416035818","https://openalex.org/W4416034542","https://openalex.org/W6910743970","https://openalex.org/W7166573239","https://openalex.org/W7207829399","https://openalex.org/W7083307948","https://openalex.org/W4415330885"],"abstract_inverted_index":{"The":[0,151,165],"reliability":[1],"of":[2,10,124,161],"VLM-as-a-Judge":[3,20,137],"is":[4,175],"critical":[5],"for":[6,143],"the":[7,26,35,47,81,90,97,141,159,162,178],"automatic":[8],"evaluation":[9],"vision-language":[11],"models":[12,107],"(VLMs).Despite":[13],"recent":[14],"progress,":[15],"our":[16],"analysis":[17],"reveals":[18,129],"that":[19,76,111],"often":[21,32],"pays":[22],"limited":[23],"attention":[24],"to":[25,102,118,126],"image":[27,48,82,152],"when":[28,40],"making":[29],"decisions.Instead,":[30],"they":[31,41],"blindly":[33],"favor":[34],"more":[36,144],"informative":[37],"answer,":[38],"even":[39],"can":[42],"recognize":[43],"it":[44],"conflicts":[45],"with":[46,69,80],"content.We":[49],"call":[50],"this":[51,93],"problem":[52],"informativeness":[53,101,114],"bias,":[54],"which":[55],"significantly":[56],"undermines":[57],"judge":[58],"reliability.To":[59],"address":[60],"it,":[61],"we":[62],"propose":[63],"BIRCH":[64,112],"(Balanced":[65],"Informativeness":[66],"and":[67,87,108,139],"CoRrectness":[68],"a":[70,73],"Truthful":[71],"AnCHor),":[72],"judging":[74],"paradigm":[75],"first":[77],"corrects":[78],"inconsistencies":[79],"content":[83],"in":[84,121,135,168],"candidate":[85],"answers,":[86],"then":[88],"compares":[89],"answers":[91],"against":[92],"corrected":[94],"version.This":[95],"shifts":[96],"judge's":[98],"focus":[99],"from":[100],"image-grounded":[103],"correctness.Experiments":[104],"on":[105,177],"multiple":[106],"benchmarks":[109],"show":[110],"reduces":[113],"bias":[115],"by":[116],"up":[117,125],"17%,":[119],"resulting":[120],"performance":[122],"gains":[123],"9.8%.Our":[127],"work":[128],"an":[130],"overlooked":[131],"but":[132],"fundamental":[133],"flaw":[134],"current":[136],"systems":[138],"highlights":[140],"need":[142],"principled":[145],"designs.Preference:":[146],"Answer":[147,149],"A":[148],"A:":[150],"does":[153],"not":[154],"provide":[155],"explicit":[156],"information":[157],"about":[158],"name":[160,174],"park.Answer":[163],"B:":[164],"benches":[166],"reside":[167],"Concord":[169],"Pacific":[170],"Place":[171],"Park.The":[172],"park's":[173],"inscribed":[176],"bench.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}